hw 3 - March 13

library(readr)  # for read_csv
library(knitr)  # for kable

income <- "https://raw.githubusercontent.com/datavizualization11/sta553/main/data/income_per_person.csv"
life <- "https://raw.githubusercontent.com/datavizualization11/sta553/main/data/life_expectancy_years.csv"
population <- "https://raw.githubusercontent.com/datavizualization11/sta553/main/data/population_total.csv"
country <- "https://raw.githubusercontent.com/datavizualization11/sta553/main/data/countries_total.csv"

incomeperperson <- read_csv(income)
lifeexpentancy <- read_csv(life)
populationsize <- read_csv(population)
countryregions <- read_csv(country)

0.1 Reshape data set: Income Per Person & Life Expectancy in Years

library(tidyverse)
income.longitudinal <- incomeperperson %>%
  gather(key = "Year",
         value = "Income",
         - geo,
         na.rm = TRUE)

income.longitudinal<- rename(income.longitudinal, Country = geo )

lifeexp.longitudinal <- lifeexpentancy %>%
  gather(key = "Year",
         value = "lifeExp",
         - geo,
         na.rm = TRUE)
lifeexp.longitudinal<- rename(lifeexp.longitudinal, Country = geo )

population.longitudinal <- populationsize %>%
  gather(key = "Year",
         value = "Population",
         - geo,
         na.rm = TRUE)
population.longitudinal<- rename(population.longitudinal, Country = geo )

0.2 Merge the datasets

LifeExpIncom <- merge(income.longitudinal, lifeexp.longitudinal, by=c("Year","Country"))

#Final Dataset
LifeExpIncomPop <-merge(LifeExpIncom, population.longitudinal, by=c("Year","Country"))

0.3 Subset - 2015 dataset

LifeExpIncomPop15 <- subset( LifeExpIncomPop, LifeExpIncomPop$Year == 2015 )

myPlotlyLayout <- function(){
  layout(  
      ## graphic size
      with = 700,
      height = 700,
      ### Title 
      title =list(text = "Association Between Life Expectancy And Income For The Year 2015", 
                          font = list(family = "Times New Roman",  # HTML font family  
                                        size = 18,
                                       color = "red")), 
      ### legend
      legend = list(title = list(text = 'Countries',
                                 font = list(family = "Courier New",
                                               size = 14,
                                              color = "green")),
                    bgcolor = "ivory",
                    bordercolor = "navy",
                    groupclick = "togglegroup",  # one of  "toggleitem" AND "togglegroup".
                    orientation = "v"  # Sets the orientation of the legend.
                    
                    ),
      ## margin of the plot
      margin = list(
              b = 120,
              l = 50,
              t = 120,
              r = 50
      ),
      ## Background
      plot_bgcolor ='#f7f7f7', 
      ## Axes labels
             xaxis = list( 
                    title=list(text = 'Life Expectancy',
                               font = list(family = 'Arial')),
                    zerolinecolor = 'red', 
                    zerolinewidth = 2, 
                    gridcolor = 'white'), 
            yaxis = list( 
                    title=list(text = 'Income',
                               font = list(family = 'Arial')),
                    zerolinecolor = 'purple', 
                    zerolinewidth = 2, 
                    gridcolor = 'white'),
       ## annotations
       annotations = list(  
                     x = 80,   # between 0 and 1. 0 = left, 1 = right
                     y = 60,   # between 0 and 1, 0 = bottom, 1 = top
                  font = list(size = 12,
                              color = "darkred"),   
                  text = "The point size is population of each country",   
                  xref = "paper",  # "container" spans the entire `width` of the plot. 
                                   # "paper" refers to the width of the plotting area only.  
                  yref = "paper",  #  same as xref
               xanchor = "center", #  horizontal alignment with respect to its x position
               yanchor = "bottom", #  similar to xanchor  
             showarrow = FALSE  ,
             ## using the following hovertemplate() to add the information of the
     ## two numerical variable to the hover text.
     hovertemplate = paste('<i><b>Income<b></i>: %{y}',
                           '<br><b>lifeExpe</b>:  %{x}',
                           '<br><b>%{Country}</b>'),
           )
  )
}

plot_ly(
    data = LifeExpIncomPop15,
    x = ~lifeExp,  # Horizontal axis 
    y = ~Income,   # Vertical axis 
    color = ~factor(Country),  # must be a numeric factor
     text = ~Population,  # show the Country in the hover text

     alpha  = 0.9,
     size = LifeExpIncomPop15$Population,
     type = "scatter",
     mode = "markers",
        ## two numerical variable to the hover text.
     hovertemplate = paste('<i><b>Income<b></i>: %{y}',
                           '<br><b>lifeExp</b>:  %{x}')
   ) 

##Animated scatter plot that shows pattern of change in the relationship between life expectancy and income over the years

regions <- countryregions[ , c("name", "region")]  
regions<- rename(regions, Country = name ) 

LifeExpIncomPop.Reg <- merge(regions, LifeExpIncomPop, by = c("Country"))

LifeExpIncomPop.Reg <- na.omit(LifeExpIncomPop.Reg)

library(gapminder)
library(gganimate)

w <- ggplot(gapminder, aes(x = LifeExpIncomPop.Reg$Income, 
                           y = LifeExpIncomPop.Reg$lifeExp, 
                           size = LifeExpIncomPop.Reg$Population,
                           colour = LifeExpIncomPop.Reg$region)) +
           geom_point(alpha = 0.7, show.legend = FALSE) +
           scale_colour_manual(values = country_colors) +
           #scale_color_manual(values=c("dodgerblue4", "darkolivegreen4","darkorchid3")) +
           #scale_color_brewer(palette="Set1") +
           scale_size(range = c(2, 12)) +
           scale_x_log10() +
           # break down the previous single plot by continent 
           facet_wrap(~region) +     # create multiple panels according to the continents
           # Here comes the gganimate specific bits
           labs(title = 'Year: {frame_time}', 
                    x = 'Income',
                    y = 'life expectancy') +
           transition_time(year) +
           ease_aes('linear')

animate(w, renderer = gifski_renderer(),
          rewind = TRUE)

Error in `combine_vars()`:
! At least one layer must contain all faceting variables: `region`.
* Plot is missing `region`
* Layer 1 is missing `region`
Backtrace:
  1. gganimate::animate(w, renderer = gifski_renderer(), rewind = TRUE)
  2. gganimate:::animate.gganim(w, renderer = gifski_renderer(), rewind = TRUE)
  3. gganimate:::prerender(plot, nframes_total)
  5. gganimate:::ggplot_build.gganim(plot)
  6. layout$setup(data, plot$data, plot$plot_env)
  7. ggplot2 f(..., self = self)
  8. self$facet$compute_layout(data, self$facet_params)
  9. ggplot2 f(...)
 12. ggplot2::combine_vars(data, params$plot_env, vars, drop = params$drop)

library(gapminder)

p <- ggplot(gapminder, aes(x = LifeExpIncomPop.Reg$Income, 
                           y = LifeExpIncomPop.Reg$lifeExp, 
                           size = LifeExpIncomPop.Reg$Population,
                           colour = LifeExpIncomPop.Reg$region)) +
        geom_point(aes(size = population, ids = region ),
                   show.legend = FALSE, 
                   alpha = 0.7) +
        scale_color_viridis_d() +      # color pallets 
        scale_size(range = c(2, 12)) +
        scale_x_log10() +
        labs(x = "GDP per capita", 
             y = "Life expectancy") +
        ## gganimate command
       transition_time(year)
## 
anim_save("LifeExp.gif", p)

gas <- "https://raw.githubusercontent.com/datavizualization11/sta553/main/data/POC.csv"

gas.station <- read_csv(gas)

# r sample - simple random sampling in r to pick 500
sample.500 <- gas.station[sample(nrow(gas.station), 500), ]

write.csv(sample.500,"C:\\Users\\agrimamahlawat\\Desktop\\SPRING 22\\sample500gas.csv", row.names = FALSE)